andreas.czerniak
/
BrBETA_dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge branch 'beta' into dedup_whitelist

This commit is contained in:
Claudio Atzori 2021-09-27 16:41:25 +02:00
parent 7fa60e166e a53acfbc06
commit 474117c2e8
21 changed files with 1300 additions and 490 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidAuthors.java
View File

@ -12,10 +12,6 @@ import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.JavaSparkContext;
@ -25,8 +21,12 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData; import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData;
import eu.dnetlib.doiboost.orcid.util.DownloadsReport;
import eu.dnetlib.doiboost.orcid.util.HDFSUtil; import eu.dnetlib.doiboost.orcid.util.HDFSUtil;
import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector;
import scala.Tuple2; import scala.Tuple2;
public class SparkDownloadOrcidAuthors { public class SparkDownloadOrcidAuthors {
@ -72,16 +72,12 @@ public class SparkDownloadOrcidAuthors {
LongAccumulator parsedRecordsAcc = spark.sparkContext().longAccumulator("parsed_records"); LongAccumulator parsedRecordsAcc = spark.sparkContext().longAccumulator("parsed_records");
LongAccumulator modifiedRecordsAcc = spark.sparkContext().longAccumulator("to_download_records"); LongAccumulator modifiedRecordsAcc = spark.sparkContext().longAccumulator("to_download_records");
LongAccumulator downloadedRecordsAcc = spark.sparkContext().longAccumulator("downloaded_records"); LongAccumulator downloadedRecordsAcc = spark.sparkContext().longAccumulator("downloaded_records");
LongAccumulator errorHTTP403Acc = spark.sparkContext().longAccumulator("error_HTTP_403"); LongAccumulator errorsAcc = spark.sparkContext().longAccumulator("errors");
LongAccumulator errorHTTP404Acc = spark.sparkContext().longAccumulator("error_HTTP_404");
LongAccumulator errorHTTP409Acc = spark.sparkContext().longAccumulator("error_HTTP_409");
LongAccumulator errorHTTP503Acc = spark.sparkContext().longAccumulator("error_HTTP_503");
LongAccumulator errorHTTP525Acc = spark.sparkContext().longAccumulator("error_HTTP_525");
LongAccumulator errorHTTPGenericAcc = spark.sparkContext().longAccumulator("error_HTTP_Generic");
logger.info("Retrieving data from lamda sequence file"); String lambdaFilePath = workingPath + lambdaFileName;
logger.info("Retrieving data from lamda sequence file: " + lambdaFilePath);
JavaPairRDD<Text, Text> lamdaFileRDD = sc JavaPairRDD<Text, Text> lamdaFileRDD = sc
.sequenceFile(workingPath + lambdaFileName, Text.class, Text.class); .sequenceFile(lambdaFilePath, Text.class, Text.class);
final long lamdaFileRDDCount = lamdaFileRDD.count(); final long lamdaFileRDDCount = lamdaFileRDD.count();
logger.info("Data retrieved: {}", lamdaFileRDDCount); logger.info("Data retrieved: {}", lamdaFileRDDCount);
@ -102,47 +98,44 @@ public class SparkDownloadOrcidAuthors {
final DownloadedRecordData downloaded = new DownloadedRecordData(); final DownloadedRecordData downloaded = new DownloadedRecordData();
downloaded.setOrcidId(orcidId); downloaded.setOrcidId(orcidId);
downloaded.setLastModifiedDate(lastModifiedDate); downloaded.setLastModifiedDate(lastModifiedDate);
CloseableHttpClient client = HttpClients.createDefault(); final HttpClientParams clientParams = new HttpClientParams();
HttpGet httpGet = new HttpGet("https://api.orcid.org/v3.0/" + orcidId + "/record"); MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams);
httpGet.addHeader("Accept", "application/vnd.orcid+xml"); httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER);
httpGet.addHeader("Authorization", String.format("Bearer %s", token)); httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml");
httpConnector.setAuthToken(token);
String apiUrl = "https://api.orcid.org/v3.0/" + orcidId + "/record";
DownloadsReport report = new DownloadsReport();
long startReq = System.currentTimeMillis(); long startReq = System.currentTimeMillis();
CloseableHttpResponse response = client.execute(httpGet); boolean downloadCompleted = false;
String record = "";
try {
record = httpConnector.getInputSource(apiUrl, report);
downloadCompleted = true;
} catch (CollectorException ce) {
if (!report.isEmpty()) {
int errCode = report.keySet().stream().findFirst().get();
report.forEach((k, v) -> {
logger.error(k + " " + v);
});
downloaded.setStatusCode(errCode);
} else {
downloaded.setStatusCode(-4);
}
errorsAcc.add(1);
}
long endReq = System.currentTimeMillis(); long endReq = System.currentTimeMillis();
long reqTime = endReq - startReq; long reqTime = endReq - startReq;
if (reqTime < 1000) { if (reqTime < 1000) {
Thread.sleep(1000 - reqTime); Thread.sleep(1000 - reqTime);
} }
int statusCode = response.getStatusLine().getStatusCode(); if (downloadCompleted) {
downloaded.setStatusCode(statusCode); downloaded.setStatusCode(200);
if (statusCode != 200) {
switch (statusCode) {
case 403:
errorHTTP403Acc.add(1);
break;
case 404:
errorHTTP404Acc.add(1);
break;
case 409:
errorHTTP409Acc.add(1);
break;
case 503:
errorHTTP503Acc.add(1);
break;
case 525:
errorHTTP525Acc.add(1);
break;
default:
errorHTTPGenericAcc.add(1);
}
return downloaded.toTuple2();
}
downloadedRecordsAcc.add(1); downloadedRecordsAcc.add(1);
downloaded downloaded
.setCompressedData( .setCompressedData(
ArgumentApplicationParser ArgumentApplicationParser
.compressArgument(IOUtils.toString(response.getEntity().getContent()))); .compressArgument(record));
client.close(); }
return downloaded.toTuple2(); return downloaded.toTuple2();
}; };
@ -153,26 +146,17 @@ public class SparkDownloadOrcidAuthors {
long authorsModifiedCount = authorsModifiedRDD.count(); long authorsModifiedCount = authorsModifiedRDD.count();
logger.info("Authors modified count: {}", authorsModifiedCount); logger.info("Authors modified count: {}", authorsModifiedCount);
logger.info("Start downloading ...");
final JavaPairRDD<Text, Text> pairRDD = authorsModifiedRDD final JavaPairRDD<Text, Text> pairRDD = authorsModifiedRDD
.repartition(100) .repartition(100)
.map(downloadRecordFn) .map(downloadRecordFn)
.mapToPair(t -> new Tuple2<>(new Text(t._1()), new Text(t._2()))); .mapToPair(t -> new Tuple2<>(new Text(t._1()), new Text(t._2())));
saveAsSequenceFile(workingPath, outputPath, sc, pairRDD); saveAsSequenceFile(workingPath, outputPath, sc, pairRDD);
logger.info("parsedRecordsAcc: {}", parsedRecordsAcc.value()); logger.info("parsedRecordsAcc: {}", parsedRecordsAcc.value());
logger.info("modifiedRecordsAcc: {}", modifiedRecordsAcc.value()); logger.info("modifiedRecordsAcc: {}", modifiedRecordsAcc.value());
logger.info("downloadedRecordsAcc: {}", downloadedRecordsAcc.value()); logger.info("downloadedRecordsAcc: {}", downloadedRecordsAcc.value());
logger.info("errorHTTP403Acc: {}", errorHTTP403Acc.value()); logger.info("errorsAcc: {}", errorsAcc.value());
logger.info("errorHTTP404Acc: {}", errorHTTP404Acc.value());
logger.info("errorHTTP409Acc: {}", errorHTTP409Acc.value());
logger.info("errorHTTP503Acc: {}", errorHTTP503Acc.value());
logger.info("errorHTTP525Acc: {}", errorHTTP525Acc.value());
logger.info("errorHTTPGenericAcc: {}", errorHTTPGenericAcc.value());
}); });
} }
private static void saveAsSequenceFile(String workingPath, String outputPath, JavaSparkContext sc, private static void saveAsSequenceFile(String workingPath, String outputPath, JavaSparkContext sc,

84
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidWorks.java
View File

@ -11,10 +11,6 @@ import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils; import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.GzipCodec; import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.JavaSparkContext;
@ -28,8 +24,12 @@ import com.google.gson.JsonElement;
import com.google.gson.JsonParser; import com.google.gson.JsonParser;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData; import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData;
import eu.dnetlib.doiboost.orcid.util.DownloadsReport;
import eu.dnetlib.doiboost.orcid.util.HDFSUtil; import eu.dnetlib.doiboost.orcid.util.HDFSUtil;
import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector;
import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser; import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser;
import scala.Tuple2; import scala.Tuple2;
@ -90,12 +90,7 @@ public class SparkDownloadOrcidWorks {
.sparkContext() .sparkContext()
.longAccumulator("error_parsing_xml_found"); .longAccumulator("error_parsing_xml_found");
LongAccumulator downloadedRecordsAcc = spark.sparkContext().longAccumulator("downloaded_records"); LongAccumulator downloadedRecordsAcc = spark.sparkContext().longAccumulator("downloaded_records");
LongAccumulator errorHTTP403Acc = spark.sparkContext().longAccumulator("error_HTTP_403"); LongAccumulator errorsAcc = spark.sparkContext().longAccumulator("errors");
LongAccumulator errorHTTP404Acc = spark.sparkContext().longAccumulator("error_HTTP_404");
LongAccumulator errorHTTP409Acc = spark.sparkContext().longAccumulator("error_HTTP_409");
LongAccumulator errorHTTP503Acc = spark.sparkContext().longAccumulator("error_HTTP_503");
LongAccumulator errorHTTP525Acc = spark.sparkContext().longAccumulator("error_HTTP_525");
LongAccumulator errorHTTPGenericAcc = spark.sparkContext().longAccumulator("error_HTTP_Generic");
JavaPairRDD<Text, Text> updatedAuthorsRDD = sc JavaPairRDD<Text, Text> updatedAuthorsRDD = sc
.sequenceFile(workingPath + "downloads/updated_authors/*", Text.class, Text.class); .sequenceFile(workingPath + "downloads/updated_authors/*", Text.class, Text.class);
@ -149,51 +144,44 @@ public class SparkDownloadOrcidWorks {
final DownloadedRecordData downloaded = new DownloadedRecordData(); final DownloadedRecordData downloaded = new DownloadedRecordData();
downloaded.setOrcidId(orcidId); downloaded.setOrcidId(orcidId);
downloaded.setLastModifiedDate(lastUpdateValue); downloaded.setLastModifiedDate(lastUpdateValue);
CloseableHttpClient client = HttpClients.createDefault(); final HttpClientParams clientParams = new HttpClientParams();
HttpGet httpGet = new HttpGet("https://api.orcid.org/v3.0/" + relativeWorkUrl); MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams);
httpGet.addHeader("Accept", "application/vnd.orcid+xml"); httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER);
httpGet.addHeader("Authorization", String.format("Bearer %s", token)); httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml");
httpConnector.setAuthToken(token);
String apiUrl = "https://api.orcid.org/v3.0/" + relativeWorkUrl;
DownloadsReport report = new DownloadsReport();
long startReq = System.currentTimeMillis(); long startReq = System.currentTimeMillis();
CloseableHttpResponse response = client.execute(httpGet); boolean downloadCompleted = false;
String record = "";
try {
record = httpConnector.getInputSource(apiUrl, report);
downloadCompleted = true;
} catch (CollectorException ce) {
if (!report.isEmpty()) {
int errCode = report.keySet().stream().findFirst().get();
report.forEach((k, v) -> {
logger.error(k + " " + v);
});
downloaded.setStatusCode(errCode);
} else {
downloaded.setStatusCode(-4);
}
errorsAcc.add(1);
}
long endReq = System.currentTimeMillis(); long endReq = System.currentTimeMillis();
long reqTime = endReq - startReq; long reqTime = endReq - startReq;
if (reqTime < 1000) { if (reqTime < 1000) {
Thread.sleep(1000 - reqTime); Thread.sleep(1000 - reqTime);
} }
int statusCode = response.getStatusLine().getStatusCode(); if (downloadCompleted) {
downloaded.setStatusCode(statusCode); downloaded.setStatusCode(200);
if (statusCode != 200) {
switch (statusCode) {
case 403:
errorHTTP403Acc.add(1);
break;
case 404:
errorHTTP404Acc.add(1);
break;
case 409:
errorHTTP409Acc.add(1);
break;
case 503:
errorHTTP503Acc.add(1);
break;
case 525:
errorHTTP525Acc.add(1);
break;
default:
errorHTTPGenericAcc.add(1);
logger
.info(
"Downloading {} status code: {}", orcidId,
response.getStatusLine().getStatusCode());
}
return downloaded.toTuple2();
}
downloadedRecordsAcc.add(1); downloadedRecordsAcc.add(1);
downloaded downloaded
.setCompressedData( .setCompressedData(
ArgumentApplicationParser ArgumentApplicationParser
.compressArgument(IOUtils.toString(response.getEntity().getContent()))); .compressArgument(record));
client.close(); }
return downloaded.toTuple2(); return downloaded.toTuple2();
}; };
@ -214,11 +202,7 @@ public class SparkDownloadOrcidWorks {
logger.info("errorLoadingXMLFoundAcc: {}", errorLoadingXMLFoundAcc.value()); logger.info("errorLoadingXMLFoundAcc: {}", errorLoadingXMLFoundAcc.value());
logger.info("errorParsingXMLFoundAcc: {}", errorParsingXMLFoundAcc.value()); logger.info("errorParsingXMLFoundAcc: {}", errorParsingXMLFoundAcc.value());
logger.info("downloadedRecordsAcc: {}", downloadedRecordsAcc.value()); logger.info("downloadedRecordsAcc: {}", downloadedRecordsAcc.value());
logger.info("errorHTTP403Acc: {}", errorHTTP403Acc.value()); logger.info("errorsAcc: {}", errorsAcc.value());
logger.info("errorHTTP409Acc: {}", errorHTTP409Acc.value());
logger.info("errorHTTP503Acc: {}", errorHTTP503Acc.value());
logger.info("errorHTTP525Acc: {}", errorHTTP525Acc.value());
logger.info("errorHTTPGenericAcc: {}", errorHTTPGenericAcc.value());
}); });
} }

10
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/DownloadsReport.java Normal file
View File

@ -0,0 +1,10 @@
package eu.dnetlib.doiboost.orcid.util;
import java.util.LinkedHashMap;
public class DownloadsReport extends LinkedHashMap<Integer, String> {
public DownloadsReport() {
}
}

272
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/MultiAttemptsHttpConnector.java Normal file
View File

@ -0,0 +1,272 @@
package eu.dnetlib.doiboost.orcid.util;
import static eu.dnetlib.dhp.utils.DHPUtils.MAPPER;
import java.io.IOException;
import java.io.InputStream;
import java.net.*;
import java.util.List;
import java.util.Map;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.math.NumberUtils;
import org.apache.http.HttpHeaders;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
/**
* Derived from eu.dnetlib.dhp.common.collection.HttpConnector2 with custom report and Bearer auth
*
* @author enrico
*/
public class MultiAttemptsHttpConnector {
private static final Logger log = LoggerFactory.getLogger(MultiAttemptsHttpConnector.class);
private HttpClientParams clientParams;
private String responseType = null;
private static final String userAgent = "Mozilla/5.0 (compatible; OAI; +http://www.openaire.eu)";
private String authToken = "";
private String acceptHeaderValue = "";
private String authMethod = "";
public final static String BEARER = "BEARER";
public MultiAttemptsHttpConnector() {
this(new HttpClientParams());
}
public MultiAttemptsHttpConnector(HttpClientParams clientParams) {
this.clientParams = clientParams;
CookieHandler.setDefault(new CookieManager(null, CookiePolicy.ACCEPT_ALL));
}
/**
* Given the URL returns the content via HTTP GET
*
* @param requestUrl the URL
* @param report the list of errors
* @return the content of the downloaded resource
* @throws CollectorException when retrying more than maxNumberOfRetry times
*/
public String getInputSource(final String requestUrl, DownloadsReport report)
throws CollectorException {
return attemptDownloadAsString(requestUrl, 1, report);
}
private String attemptDownloadAsString(final String requestUrl, final int retryNumber,
final DownloadsReport report) throws CollectorException {
try (InputStream s = attemptDownload(requestUrl, retryNumber, report)) {
return IOUtils.toString(s);
} catch (IOException e) {
log.error(e.getMessage(), e);
throw new CollectorException(e);
}
}
private InputStream attemptDownload(final String requestUrl, final int retryNumber,
final DownloadsReport report) throws CollectorException, IOException {
if (retryNumber > getClientParams().getMaxNumberOfRetry()) {
final String msg = String
.format(
"Max number of retries (%s/%s) exceeded, failing.",
retryNumber, getClientParams().getMaxNumberOfRetry());
log.error(msg);
throw new CollectorException(msg);
}
log.info("Request attempt {} [{}]", retryNumber, requestUrl);
InputStream input = null;
try {
if (getClientParams().getRequestDelay() > 0) {
backoffAndSleep(getClientParams().getRequestDelay());
}
final HttpURLConnection urlConn = (HttpURLConnection) new URL(requestUrl).openConnection();
urlConn.setInstanceFollowRedirects(false);
urlConn.setReadTimeout(getClientParams().getReadTimeOut() * 1000);
urlConn.setConnectTimeout(getClientParams().getConnectTimeOut() * 1000);
urlConn.addRequestProperty(HttpHeaders.USER_AGENT, userAgent);
if (!getAcceptHeaderValue().isEmpty()) {
urlConn.addRequestProperty(HttpHeaders.ACCEPT, getAcceptHeaderValue());
}
if (!getAuthToken().isEmpty() && getAuthMethod().equals(BEARER)) {
urlConn.addRequestProperty(HttpHeaders.AUTHORIZATION, String.format("Bearer %s", getAuthToken()));
}
if (log.isDebugEnabled()) {
logHeaderFields(urlConn);
}
int retryAfter = obtainRetryAfter(urlConn.getHeaderFields());
if (is2xx(urlConn.getResponseCode())) {
input = urlConn.getInputStream();
responseType = urlConn.getContentType();
return input;
}
if (is3xx(urlConn.getResponseCode())) {
// REDIRECTS
final String newUrl = obtainNewLocation(urlConn.getHeaderFields());
log.info("The requested url has been moved to {}", newUrl);
report
.put(
urlConn.getResponseCode(),
String.format("Moved to: %s", newUrl));
urlConn.disconnect();
if (retryAfter > 0) {
backoffAndSleep(retryAfter);
}
return attemptDownload(newUrl, retryNumber + 1, report);
}
if (is4xx(urlConn.getResponseCode()) || is5xx(urlConn.getResponseCode())) {
switch (urlConn.getResponseCode()) {
case HttpURLConnection.HTTP_NOT_FOUND:
case HttpURLConnection.HTTP_BAD_GATEWAY:
case HttpURLConnection.HTTP_UNAVAILABLE:
case HttpURLConnection.HTTP_GATEWAY_TIMEOUT:
if (retryAfter > 0) {
log
.warn(
"{} - waiting and repeating request after suggested retry-after {} sec.",
requestUrl, retryAfter);
backoffAndSleep(retryAfter * 1000);
} else {
log
.warn(
"{} - waiting and repeating request after default delay of {} sec.",
requestUrl, getClientParams().getRetryDelay());
backoffAndSleep(retryNumber * getClientParams().getRetryDelay() * 1000);
}
report.put(urlConn.getResponseCode(), requestUrl);
urlConn.disconnect();
return attemptDownload(requestUrl, retryNumber + 1, report);
default:
report
.put(
urlConn.getResponseCode(),
String
.format(
"%s Error: %s", requestUrl, urlConn.getResponseMessage()));
throw new CollectorException(urlConn.getResponseCode() + " error " + report);
}
}
throw new CollectorException(
String
.format(
"Unexpected status code: %s errors: %s", urlConn.getResponseCode(),
MAPPER.writeValueAsString(report)));
} catch (MalformedURLException | UnknownHostException e) {
log.error(e.getMessage(), e);
report.put(-2, e.getMessage());
throw new CollectorException(e.getMessage(), e);
} catch (SocketTimeoutException | SocketException e) {
log.error(e.getMessage(), e);
report.put(-3, e.getMessage());
backoffAndSleep(getClientParams().getRetryDelay() * retryNumber * 1000);
return attemptDownload(requestUrl, retryNumber + 1, report);
}
}
private void logHeaderFields(final HttpURLConnection urlConn) throws IOException {
log.debug("StatusCode: {}", urlConn.getResponseMessage());
for (Map.Entry<String, List<String>> e : urlConn.getHeaderFields().entrySet()) {
if (e.getKey() != null) {
for (String v : e.getValue()) {
log.debug(" key: {} - value: {}", e.getKey(), v);
}
}
}
}
private void backoffAndSleep(int sleepTimeMs) throws CollectorException {
log.info("I'm going to sleep for {}ms", sleepTimeMs);
try {
Thread.sleep(sleepTimeMs);
} catch (InterruptedException e) {
log.error(e.getMessage(), e);
throw new CollectorException(e);
}
}
private int obtainRetryAfter(final Map<String, List<String>> headerMap) {
for (String key : headerMap.keySet()) {
if ((key != null) && key.equalsIgnoreCase(HttpHeaders.RETRY_AFTER) && (!headerMap.get(key).isEmpty())
&& NumberUtils.isCreatable(headerMap.get(key).get(0))) {
return Integer.parseInt(headerMap.get(key).get(0)) + 10;
}
}
return -1;
}
private String obtainNewLocation(final Map<String, List<String>> headerMap) throws CollectorException {
for (String key : headerMap.keySet()) {
if ((key != null) && key.equalsIgnoreCase(HttpHeaders.LOCATION) && (headerMap.get(key).size() > 0)) {
return headerMap.get(key).get(0);
}
}
throw new CollectorException("The requested url has been MOVED, but 'location' param is MISSING");
}
private boolean is2xx(final int statusCode) {
return statusCode >= 200 && statusCode <= 299;
}
private boolean is4xx(final int statusCode) {
return statusCode >= 400 && statusCode <= 499;
}
private boolean is3xx(final int statusCode) {
return statusCode >= 300 && statusCode <= 399;
}
private boolean is5xx(final int statusCode) {
return statusCode >= 500 && statusCode <= 599;
}
public String getResponseType() {
return responseType;
}
public HttpClientParams getClientParams() {
return clientParams;
}
public void setClientParams(HttpClientParams clientParams) {
this.clientParams = clientParams;
}
public void setAuthToken(String authToken) {
this.authToken = authToken;
}
private String getAuthToken() {
return authToken;
}
public String getAcceptHeaderValue() {
return acceptHeaderValue;
}
public void setAcceptHeaderValue(String acceptHeaderValue) {
this.acceptHeaderValue = acceptHeaderValue;
}
public String getAuthMethod() {
return authMethod;
}
public void setAuthMethod(String authMethod) {
this.authMethod = authMethod;
}
}

92
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/OrcidClientTest.java
View File

@ -1,13 +1,11 @@
package eu.dnetlib.doiboost.orcid; package eu.dnetlib.doiboost.orcid;
import static org.junit.jupiter.api.Assertions.assertEquals; import static org.junit.jupiter.api.Assertions.*;
import static org.junit.jupiter.api.Assertions.assertTrue;
import java.io.*; import java.io.*;
import java.nio.file.Files; import java.nio.file.Files;
import java.nio.file.Path; import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.StandardOpenOption; import java.nio.file.StandardOpenOption;
import java.text.ParseException; import java.text.ParseException;
import java.text.SimpleDateFormat; import java.text.SimpleDateFormat;
@ -17,7 +15,6 @@ import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream; import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream; import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
import org.apache.commons.compress.utils.Lists; import org.apache.commons.compress.utils.Lists;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.http.client.methods.CloseableHttpResponse; import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet; import org.apache.http.client.methods.HttpGet;
@ -28,8 +25,11 @@ import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test; import org.junit.jupiter.api.Test;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.common.collection.HttpClientParams;
import eu.dnetlib.dhp.schema.orcid.AuthorData; import eu.dnetlib.dhp.schema.orcid.AuthorData;
import eu.dnetlib.doiboost.orcid.xml.XMLRecordParserTest; import eu.dnetlib.doiboost.orcid.util.DownloadsReport;
import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector;
import jdk.nashorn.internal.ir.annotations.Ignore; import jdk.nashorn.internal.ir.annotations.Ignore;
public class OrcidClientTest { public class OrcidClientTest {
@ -49,7 +49,7 @@ public class OrcidClientTest {
@BeforeAll @BeforeAll
private static void setUp() throws IOException { private static void setUp() throws IOException {
testPath = Files.createTempDirectory(XMLRecordParserTest.class.getName()); testPath = Files.createTempDirectory(OrcidClientTest.class.getName());
System.out.println("using test path: " + testPath); System.out.println("using test path: " + testPath);
} }
@ -349,4 +349,84 @@ public class OrcidClientTest {
final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork); final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork);
logToFile(testPath, "\n\nwork updated \n\n" + work); logToFile(testPath, "\n\nwork updated \n\n" + work);
} }
@Test
void downloadUnknownHostExceptionTest() throws Exception {
logToFile(testPath, "downloadUnknownHostExceptionTest");
final String orcid = "0000-0001-7291-3210";
final HttpClientParams clientParams = new HttpClientParams();
clientParams.setMaxNumberOfRetry(2);
MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams);
httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER);
httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml");
httpConnector.setAuthToken("78fdb232-7105-4086-8570-e153f4198e3d");
String wrongApiUrl = "https://api.orcid_UNKNOWN.org/v3.0/" + orcid + "/" + REQUEST_TYPE_RECORD;
String url = "UNKNOWN";
DownloadsReport report = new DownloadsReport();
try {
httpConnector.getInputSource(wrongApiUrl, report);
} catch (CollectorException ce) {
logToFile(testPath, "CollectorException downloading: " + ce.getMessage());
} catch (Throwable t) {
logToFile(testPath, "Throwable downloading: " + t.getMessage());
}
}
@Test
void downloadAttemptSuccessTest() throws Exception {
logToFile(testPath, "downloadAttemptSuccessTest");
final String orcid = "0000-0001-7291-3210";
final HttpClientParams clientParams = new HttpClientParams();
clientParams.setMaxNumberOfRetry(2);
MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams);
httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER);
httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml");
httpConnector.setAuthToken("78fdb232-7105-4086-8570-e153f4198e3d");
String apiUrl = "https://api.orcid.org/v3.0/" + orcid + "/" + REQUEST_TYPE_RECORD;
String url = "UNKNOWN";
DownloadsReport report = new DownloadsReport();
String record = httpConnector.getInputSource(apiUrl, report);
logToFile(testPath, "Downloaded at first attempt record: " + record);
}
@Test
void downloadAttemptNotFoundTest() throws Exception {
logToFile(testPath, "downloadAttemptNotFoundTest");
final HttpClientParams clientParams = new HttpClientParams();
clientParams.setMaxNumberOfRetry(2);
MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams);
httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER);
httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml");
httpConnector.setAuthToken("78fdb232-7105-4086-8570-e153f4198e3d");
String apiUrl = "https://api.orcid.org/v3.0/NOTFOUND/" + REQUEST_TYPE_RECORD;
DownloadsReport report = new DownloadsReport();
try {
httpConnector.getInputSource(apiUrl, report);
} catch (CollectorException ce) {
}
report.forEach((k, v) -> {
try {
logToFile(testPath, k + " " + v);
} catch (IOException e) {
e.printStackTrace();
}
});
}
@Test
@Ignore
void testDownloadedAuthor() throws Exception {
final String base64CompressedWork = "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";
final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork);
logToFile(testPath, "\n\ndownloaded author \n\n" + work);
}
@Test
@Ignore
void testDownloadedWork() throws Exception {
final String base64CompressedWork = "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";
final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork);
logToFile(testPath, "\n\ndownloaded work \n\n" + work);
}
} }

12
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java
View File

@ -76,6 +76,18 @@ public class IndexRecordTransformerTest {
testRecordTransformation(record); testRecordTransformation(record);
} }
@Test
public void testForEOSCFutureDataTransferPilot() throws IOException, TransformerException {
final String record = IOUtils.toString(getClass().getResourceAsStream("eosc-future/data-transfer-pilot.xml"));
testRecordTransformation(record);
}
@Test
public void testForEOSCFutureTraining() throws IOException, TransformerException {
final String record = IOUtils.toString(getClass().getResourceAsStream("eosc-future/training-notebooks-seadatanet.xml"));
testRecordTransformation(record);
}
private void testRecordTransformation(final String record) throws IOException, TransformerException { private void testRecordTransformation(final String record) throws IOException, TransformerException {
final String fields = IOUtils.toString(getClass().getResourceAsStream("fields.xml")); final String fields = IOUtils.toString(getClass().getResourceAsStream("fields.xml"));
final String xslt = IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl")); final String xslt = IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl"));

72
dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/data-transfer-pilot.xml Normal file
View File

@ -0,0 +1,72 @@
<record>
<result xmlns:dri="http://www.driver-repository.eu/namespace/dri" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<header>
<dri:objIdentifier>r37b0ad08687::dec0d8520e726f2adda9a51280ac7299</dri:objIdentifier>
<dri:dateOfCollection>2021-09-22T08:53:16Z</dri:dateOfCollection>
<dri:status>under curation</dri:status>
<counters />
</header>
<metadata>
<oaf:entity xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://namespace.openaire.eu/oaf http://namespace.openaire.eu/oaf http://www.openaire.eu/schema/0.2/oaf-0.2.xsd">
<oaf:result>
<title classid="main title" classname="main title" schemeid="dnet:dataCite_title" schemename="dnet:dataCite_title">EGI-Foundation/data-transfer-pilot: Include libraries in environment.yml</title>
<creator rank="1" name="" surname="">Giuseppe La Rocca</creator>
<creator rank="2" name="" surname="">Enol Fernández</creator>
<creator rank="3" name="" surname="">Andrea Manzi</creator>
<dateofacceptance />
<resulttype classid="software" classname="software" schemeid="dnet:result_typologies" schemename="dnet:result_typologies" />
<language classid="" classname="" schemeid="dnet:languages" schemename="dnet:languages" />
<description>This notebook is used to demonstrate how a scientist from one of the PaNOSC RIs can use the resources provided by EGI to perform analysis on the data sets obtained during an expirement.</description>
<country classid="" classname="" schemeid="" schemename="" />
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">EOSC Jupyter Notebook</subject>
<relevantdate classid="" classname="" schemeid="" schemename="" />
<publisher>Zenodo</publisher>
<embargoenddate />
<journal issn="" eissn="" lissn="" ep="" iss="" sp="" vol="" />
<source />
<fulltext />
<format />
<storagedate />
<resourcetype classid="" classname="" schemeid="" schemename="" />
<device />
<size />
<version />
<lastmetadataupdate />
<metadataversionnumber />
<documentationUrl />
<codeRepositoryUrl />
<programmingLanguage classid="" classname="" schemeid="" schemename="" />
<contactperson />
<contactgroup />
<tool />
<originalId>oai:zenodo.org:4218562</originalId>
<collectedfrom name="Zenodo" id="re3data_____::7b0ad08687b2c960d5aeef06f811d5e6" />
<pid classid="oai" classname="Open Archives Initiative" schemeid="dnet:pid_types" schemename="dnet:pid_types">oai:zenodo.org:4218562</pid>
<pid classid="doi" classname="Digital Object Identifier" schemeid="dnet:pid_types" schemename="dnet:pid_types">10.5281/zenodo.4218562</pid>
<bestaccessright classid="OPEN" classname="Open Access" schemeid="dnet:access_modes" schemename="dnet:access_modes" />
<datainfo>
<inferred>false</inferred>
<deletedbyinference>false</deletedbyinference>
<trust>0.9</trust>
<inferenceprovenance />
<provenanceaction classid="user:insert" classname="user:insert" schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions" />
</datainfo>
<rels></rels>
<children>
<instance id="r37b0ad08687::dec0d8520e726f2adda9a51280ac7299">
<instancetype classid="0029" classname="Software" schemeid="dnet:publication_resource" schemename="dnet:publication_resource" />
<collectedfrom name="Zenodo" id="re3data_____::7b0ad08687b2c960d5aeef06f811d5e6" />
<hostedby name="Zenodo" id="re3data_____::7b0ad08687b2c960d5aeef06f811d5e6" />
<accessright classid="OPEN" classname="Open Access" schemeid="dnet:access_modes" schemename="dnet:access_modes" />
<dateofacceptance />
<webresource>
<url>https://zenodo.org/record/4218562</url>
</webresource>
</instance>
</children>
</oaf:result>
</oaf:entity>
</metadata>
</result>
</record>

71
dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/training-notebooks-seadatanet.xml Normal file
View File

@ -0,0 +1,71 @@
<record>
<result xmlns:dri="http://www.driver-repository.eu/namespace/dri" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<header>
<dri:objIdentifier>r37b0ad08687::eb430fb7438e1533ba95d6aa50a477eb</dri:objIdentifier>
<dri:dateOfCollection>2021-09-22T08:53:13Z</dri:dateOfCollection>
<dri:status>under curation</dri:status>
<counters />
</header>
<metadata>
<oaf:entity xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://namespace.openaire.eu/oaf http://namespace.openaire.eu/oaf http://www.openaire.eu/schema/0.2/oaf-0.2.xsd">
<oaf:result>
<title classid="main title" classname="main title" schemeid="dnet:dataCite_title" schemename="dnet:dataCite_title">EGI-Foundation/training-notebooks-seadatanet: Version 0.4</title>
<creator rank="1" name="" surname="">Enol Fernández</creator>
<dateofacceptance />
<resulttype classid="software" classname="software" schemeid="dnet:result_typologies" schemename="dnet:result_typologies" />
<language classid="" classname="" schemeid="dnet:languages" schemename="dnet:languages" />
<description>A sample notebook using SeaDataNet data to plot a map that shows surface temperature of Black Sea, Arctic Sea and Baltic Sea. The data is available at EGI DataHub with PID http://hdl.handle.net/21.T15999/qVk6JWQ (run at EGI Notebooks service for easy access to data).This release updates the PID for the data.</description>
<country classid="" classname="" schemeid="" schemename="" />
<subject classid="keyword" classname="keyword" schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">EOSC Jupyter Notebook</subject>
<relevantdate classid="" classname="" schemeid="" schemename="" />
<publisher>Zenodo</publisher>
<embargoenddate />
<journal issn="" eissn="" lissn="" ep="" iss="" sp="" vol="" />
<source />
<fulltext />
<format />
<storagedate />
<resourcetype classid="" classname="" schemeid="" schemename="" />
<device />
<size />
<version />
<lastmetadataupdate />
<metadataversionnumber />
<documentationUrl />
<codeRepositoryUrl />
<programmingLanguage classid="" classname="" schemeid="" schemename="" />
<contactperson />
<contactgroup />
<tool />
<originalId>oai:zenodo.org:3561323</originalId>
<collectedfrom name="Zenodo" id="re3data_____::7b0ad08687b2c960d5aeef06f811d5e6" />
<pid classid="oai" classname="Open Archives Initiative" schemeid="dnet:pid_types" schemename="dnet:pid_types">oai:zenodo.org:3561323</pid>
<pid classid="doi" classname="Digital Object Identifier" schemeid="dnet:pid_types" schemename="dnet:pid_types">10.5281/zenodo.3561323</pid>
<bestaccessright classid="OPEN" classname="Open Access" schemeid="dnet:access_modes" schemename="dnet:access_modes" />
<datainfo>
<inferred>false</inferred>
<deletedbyinference>false</deletedbyinference>
<trust>0.9</trust>
<inferenceprovenance />
<provenanceaction classid="user:insert" classname="user:insert" schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions" />
</datainfo>
<rels></rels>
<children>
<instance id="r37b0ad08687::eb430fb7438e1533ba95d6aa50a477eb">
<instancetype classid="0029" classname="Software" schemeid="dnet:publication_resource" schemename="dnet:publication_resource" />
<collectedfrom name="Zenodo" id="re3data_____::7b0ad08687b2c960d5aeef06f811d5e6" />
<hostedby name="Zenodo" id="re3data_____::7b0ad08687b2c960d5aeef06f811d5e6" />
<accessright classid="OPEN" classname="Open Access" schemeid="dnet:access_modes" schemename="dnet:access_modes" />
<dateofacceptance />
<webresource>
<url>https://zenodo.org/record/3561323</url>
</webresource>
</instance>
</children>
</oaf:result>
</oaf:entity>
</metadata>
</result>
</record>

16
dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/fields.xml
View File

@ -15,7 +15,13 @@
<FIELD indexable="true" multivalued="false" name="datasourcecompatibilityid" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/openairecompatibility/@classid"/> <FIELD indexable="true" multivalued="false" name="datasourcecompatibilityid" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/openairecompatibility/@classid"/>
<FIELD indexable="true" multivalued="false" name="datasourcecompatibilityname" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/openairecompatibility/@classname"/> <FIELD indexable="true" multivalued="false" name="datasourcecompatibilityname" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/openairecompatibility/@classname"/>
<FIELD indexable="true" multivalued="true" name="datasourcesubject" result="false" stat="false" type="ngramtext" xpath="//*[local-name()='entity']/*[local-name()='datasource']/subjects"/> <FIELD indexable="true" multivalued="true" name="datasourcesubject" result="false" stat="false" type="ngramtext" xpath="//*[local-name()='entity']/*[local-name()='datasource']/subjects"/>
<FIELD indexable="true" name="versioning" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/versioning"/><!-- ORGANIZATION FIELDS --> <FIELD indexable="true" name="versioning" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/versioning"/>
<!-- datasource fields for EOSC -->
<FIELD indexable="true" name="datasourcejurisdiction" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/jurisdiction"/>
<FIELD indexable="true" name="datasourcethematic" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/thematic"/>
<FIELD indexable="true" name="datasourceknowledge_graph" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/knowledgegraph"/>
<FIELD indexable="true" name="datasourcecontentpolicy" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='datasource']/contentpolicy"/>
<!-- ORGANIZATION FIELDS -->
<FIELD indexable="true" name="organizationlegalshortname" result="false" stat="false" type="ngramtext" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='organization']//legalshortname)"/> <FIELD indexable="true" name="organizationlegalshortname" result="false" stat="false" type="ngramtext" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='organization']//legalshortname)"/>
<FIELD indexable="true" name="organizationlegalname" result="false" stat="false" type="ngramtext" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='organization']//legalname)"/> <FIELD indexable="true" name="organizationlegalname" result="false" stat="false" type="ngramtext" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='organization']//legalname)"/>
<FIELD indexable="true" name="organizationalternativenames" result="false" stat="false" type="ngramtext" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='organization']//alternativeNames)"/> <FIELD indexable="true" name="organizationalternativenames" result="false" stat="false" type="ngramtext" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='organization']//alternativeNames)"/>
@ -28,7 +34,8 @@
<FIELD indexable="true" name="organizationecenterprise" result="false" stat="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/ecenterprise"/> <FIELD indexable="true" name="organizationecenterprise" result="false" stat="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/ecenterprise"/>
<FIELD indexable="true" name="organizationecsmevalidated" result="false" stat="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/ecsmevalidated"/> <FIELD indexable="true" name="organizationecsmevalidated" result="false" stat="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/ecsmevalidated"/>
<FIELD indexable="true" name="organizationecnutscode" result="false" stat="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/ecnutscode"/> <FIELD indexable="true" name="organizationecnutscode" result="false" stat="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/ecnutscode"/>
<FIELD indexable="true" multivalued="false" name="organizationcountryname" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/country/@classname"/><!-- PROJECT FIELDS --> <FIELD indexable="true" multivalued="false" name="organizationcountryname" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='organization']/country/@classname"/>
<!-- PROJECT FIELDS -->
<FIELD indexable="true" name="projectcode" result="false" stat="false" type="ngramtext" xpath="//*[local-name()='entity']/*[local-name()='project']/code"/> <FIELD indexable="true" name="projectcode" result="false" stat="false" type="ngramtext" xpath="//*[local-name()='entity']/*[local-name()='project']/code"/>
<FIELD indexable="true" name="projectcode_nt" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='project']/code"/> <FIELD indexable="true" name="projectcode_nt" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']/*[local-name()='project']/code"/>
<FIELD indexable="true" name="projectacronym" result="false" stat="false" type="ngramtext" xpath="//*[local-name()='entity']/*[local-name()='project']/acronym"/> <FIELD indexable="true" name="projectacronym" result="false" stat="false" type="ngramtext" xpath="//*[local-name()='entity']/*[local-name()='project']/acronym"/>
@ -79,6 +86,7 @@
<FIELD indexable="true" multivalued="true" name="resultauthor_nt" result="false" stat="false" type="string_ci" xpath="//*[local-name()='entity']/*[local-name()='result']/creator"/> <FIELD indexable="true" multivalued="true" name="resultauthor_nt" result="false" stat="false" type="string_ci" xpath="//*[local-name()='entity']/*[local-name()='result']/creator"/>
<FIELD indexable="true" multivalued="true" name="authorid" result="false" stat="false" type="string_ci" xpath="//*[local-name()='entity']/*[local-name()='result']/creator/@*[local-name() != 'rank' and local-name() != 'name' and local-name() != 'surname']"/> <FIELD indexable="true" multivalued="true" name="authorid" result="false" stat="false" type="string_ci" xpath="//*[local-name()='entity']/*[local-name()='result']/creator/@*[local-name() != 'rank' and local-name() != 'name' and local-name() != 'surname']"/>
<FIELD indexable="true" multivalued="true" name="authoridtype" result="false" stat="false" type="string_ci" xpath="//*[local-name()='entity']/*[local-name()='result']/creator/@*[local-name() != 'rank' and local-name() != 'name' and local-name() != 'surname']/local-name()"/> <FIELD indexable="true" multivalued="true" name="authoridtype" result="false" stat="false" type="string_ci" xpath="//*[local-name()='entity']/*[local-name()='result']/creator/@*[local-name() != 'rank' and local-name() != 'name' and local-name() != 'surname']/local-name()"/>
<FIELD indexable="true" multivalued="true" name="orcidtypevalue" result="false" stat="false" type="string_ci" value="string-join((./@*[local-name() = 'orcid' or local-name() = 'orcid_pending'], ./@*[local-name() = 'orcid' or local-name() = 'orcid_pending']/local-name()), '||' )" xpath="//*[local-name()='entity']/*[local-name()='result']/creator"/>
<FIELD indexable="true" name="resulthostingdatasource" result="false" stat="false" tokenizable="false" value="distinct-values(concat(./@id, '||', ./@name))" xpath="//*[local-name()='entity']/*[local-name()='result']/children/instance/*[local-name()='hostedby']"/> <FIELD indexable="true" name="resulthostingdatasource" result="false" stat="false" tokenizable="false" value="distinct-values(concat(./@id, '||', ./@name))" xpath="//*[local-name()='entity']/*[local-name()='result']/children/instance/*[local-name()='hostedby']"/>
<FIELD indexable="true" name="resulthostingdatasourceid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='result']/children/instance/*[local-name()='hostedby']/@id)"/> <FIELD indexable="true" name="resulthostingdatasourceid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='result']/children/instance/*[local-name()='hostedby']/@id)"/>
<FIELD indexable="true" name="resulthostingdatasourcename" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='result']/children/instance/*[local-name()='hostedby']/@name)"/> <FIELD indexable="true" name="resulthostingdatasourcename" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*[local-name()='result']/children/instance/*[local-name()='hostedby']/@name)"/>
@ -105,7 +113,7 @@
<FIELD indexable="true" name="relorganizationname" result="false" stat="false" xpath="distinct-values(//*[local-name()='entity']/*//rel[./to/@type='organization']/legalname)"/> <FIELD indexable="true" name="relorganizationname" result="false" stat="false" xpath="distinct-values(//*[local-name()='entity']/*//rel[./to/@type='organization']/legalname)"/>
<FIELD indexable="true" name="relorganizationshortname" result="false" stat="false" xpath="distinct-values(//*[local-name()='entity']/*//rel[./to/@type='organization']/legalshortname)"/> <FIELD indexable="true" name="relorganizationshortname" result="false" stat="false" xpath="distinct-values(//*[local-name()='entity']/*//rel[./to/@type='organization']/legalshortname)"/>
<FIELD indexable="true" name="relresultid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*//rel/to[@type='result'])"/> <FIELD indexable="true" name="relresultid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*//rel/to[@type='result'])"/>
<FIELD indexable="true" name="relresulttype" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*//rel/to/@type)"/> <FIELD indexable="true" name="relresulttype" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*//rel/resulttype/@classid)"/>
<FIELD indexable="true" name="relclass" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*//rel/to/@class)"/> <FIELD indexable="true" name="relclass" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*//rel/to/@class)"/>
<FIELD indexable="true" name="relfundinglevel0_id" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']//rel/funding/funding_level_0"/> <FIELD indexable="true" name="relfundinglevel0_id" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']//rel/funding/funding_level_0"/>
<FIELD indexable="true" name="relfundinglevel0_name" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']//rel/funding/funding_level_0/@name/string()"/> <FIELD indexable="true" name="relfundinglevel0_name" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']//rel/funding/funding_level_0/@name/string()"/>
@ -130,7 +138,7 @@
<FIELD indexable="true" name="collectedfromdatasourceid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/*[local-name()='collectedfrom']/@id | //*[local-name()='entity']/*//*[local-name() = 'instance']/*[local-name()='collectedfrom']/@id)"/> <FIELD indexable="true" name="collectedfromdatasourceid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/*[local-name()='collectedfrom']/@id | //*[local-name()='entity']/*//*[local-name() = 'instance']/*[local-name()='collectedfrom']/@id)"/>
<FIELD indexable="true" name="collectedfromname" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/*[local-name()='collectedfrom']/@name | //*[local-name()='entity']/*//*[local-name() = 'instance']/*[local-name()='collectedfrom']/@name)"/> <FIELD indexable="true" name="collectedfromname" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/*[local-name()='collectedfrom']/@name | //*[local-name()='entity']/*//*[local-name() = 'instance']/*[local-name()='collectedfrom']/@name)"/>
<FIELD indexable="true" name="originalid" result="false" stat="false" tokenizable="false" type="string_ci" xpath="//*[local-name()='entity']/*/*[local-name()='originalId']"/> <FIELD indexable="true" name="originalid" result="false" stat="false" tokenizable="false" type="string_ci" xpath="//*[local-name()='entity']/*/*[local-name()='originalId']"/>
<FIELD indexable="true" name="pid" result="false" stat="false" tokenizable="false" type="string_ci" xpath="//*[local-name()='entity']/*/pid/text()"/> <FIELD indexable="true" name="pid" result="false" stat="false" tokenizable="false" type="string_ci" xpath="distinct-values(//*[local-name()='entity']/*/pid/text()|//*[local-name()='instance']/*[local-name()='alternateidentifier']/text())"/>
<FIELD indexable="true" name="pidclassid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/pid/@classid)"/> <FIELD indexable="true" name="pidclassid" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/pid/@classid)"/>
<FIELD indexable="true" name="pidclassname" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/pid/@classname)"/> <FIELD indexable="true" name="pidclassname" result="false" stat="false" tokenizable="false" xpath="distinct-values(//*[local-name()='entity']/*/pid/@classname)"/>
<FIELD indexable="true" name="inferred" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']//datainfo/inferred"/> <FIELD indexable="true" name="inferred" result="false" stat="false" tokenizable="false" xpath="//*[local-name()='entity']//datainfo/inferred"/>

2
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
View File

@ -16,7 +16,7 @@ curl -L ${CONTEXT_API}/contexts/?type=ri,community -H "accept: application/json"
cat contexts.csv | cut -d , -f1 | xargs -I {} curl -L ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv cat contexts.csv | cut -d , -f1 | xargs -I {} curl -L ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv
cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl -L ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl -L ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv
cat contexts.csv | sed 's/^\(.*\),\(.*\)/\1,\1::other,\2/' >> categories.csv cat contexts.csv | sed 's/^\(.*\),\(.*\)/\1,\1::other,\2/' >> categories.csv
cat categories.csv | grep -v ::other | sed 's/^.*,\(.*\),\(.*\)/\1,\1::other,\2/' >> concepts.csv cat categories.csv | sed 's/^.*,\(.*\),\(.*\)/\1,\1::other,\2/' >> concepts.csv
echo "uploading context data to hdfs" echo "uploading context data to hdfs"
hdfs dfs -mkdir ${TMP} hdfs dfs -mkdir ${TMP}

2
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/indicators.sh
View File

@ -15,5 +15,5 @@ hdfs dfs -copyToLocal $SCRIPT_PATH
echo "Creating indicators" echo "Creating indicators"
impala-shell -q "invalidate metadata" impala-shell -q "invalidate metadata"
impala-shell -d ${TARGET} -q "show tables" --delimited | sed "s/^\(.*\)/compute stats ${TARGET}.\1;/" | impala-shell -c -f - impala-shell -d ${TARGET} -q "show tables" --delimited | sed "s/^\(.*\)/compute stats ${TARGET}.\1;/" | impala-shell -c -f -
cat step16_7-createIndicatorsTables.sql | impala-shell -d $TARGET -f - cat step16-createIndicatorsTables.sql | impala-shell -d $TARGET -f -
echo "Indicators created" echo "Indicators created"

11
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory.sh → dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-post.sh
View File

@ -9,16 +9,9 @@ fi
export SOURCE=$1 export SOURCE=$1
export TARGET=$2 export TARGET=$2
export SHADOW=$3 export SHADOW=$3
export SCRIPT_PATH=$4
echo "Getting file from " $4 impala-shell -q "invalidate metadata;"
hdfs dfs -copyToLocal $4 impala-shell -d ${TARGET} -q "show tables" --delimited | sed "s/\(.*\)/compute stats ${TARGET}.\1;/" | impala-shell -f -
echo "Creating observatory database"
impala-shell -q "drop database if exists ${TARGET} cascade"
impala-shell -q "create database if not exists ${TARGET}"
impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${TARGET}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -f -
cat step21-createObservatoryDB.sql | sed s/SOURCE/$1/g | sed s/TARGET/$2/g1 | impala-shell -f -
echo "Impala shell finished" echo "Impala shell finished"
echo "Updating shadow observatory database" echo "Updating shadow observatory database"

16
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-pre.sh Normal file
View File

@ -0,0 +1,16 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
export SOURCE=$1
export TARGET=$2
export SHADOW=$3
echo "Creating observatory database"
impala-shell -q "drop database if exists ${TARGET} cascade"
impala-shell -q "create database if not exists ${TARGET}"
impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${TARGET}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -f -

5
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql
View File

@ -23,6 +23,11 @@ CREATE OR REPLACE VIEW ${stats_db_name}.rndexpediture AS
SELECT * SELECT *
FROM ${external_stats_db_name}.rndexpediture; FROM ${external_stats_db_name}.rndexpediture;
CREATE OR REPLACE VIEW ${stats_db_name}.licenses_normalized AS
SELECT *
FROM ${external_stats_db_name}.licenses_normalized;
------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------
-- Creation date of the database -- Creation date of the database

0
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql → dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15_5.sql
View File

0
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_7-createIndicatorsTables.sql → dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql
View File

62
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql
View File

@ -1,62 +0,0 @@
----------------------------------------------------
-- Shortcuts for various definitions in stats db ---
----------------------------------------------------
-- Peer reviewed:
-- Results that have been collected from Crossref
create table ${stats_db_name}.result_peerreviewed as
with peer_reviewed as (
select distinct r.id as id
from ${stats_db_name}.result r
join ${stats_db_name}.result_sources rs on rs.id=r.id
join ${stats_db_name}.datasource d on d.id=rs.datasource
where d.name='Crossref')
select distinct peer_reviewed.id as id, true as peer_reviewed
from peer_reviewed
union all
select distinct r.id as id, false as peer_reviewed
from ${stats_db_name}.result r
left outer join peer_reviewed pr on pr.id=r.id
where pr.id is null;
-- Green OA:
-- OA results that are hosted by an Institutional repository and have NOT been harvested from a DOAJ journal.
create table ${stats_db_name}.result_greenoa as
with result_green as (
select distinct r.id as id
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource
left outer join (
select rd.id from ${stats_db_name}.result_datasources rd
join ${stats_db_name}.datasource d on rd.datasource=d.id
join ${stats_db_name}.datasource_sources sds on sds.id=d.id
join ${stats_db_name}.datasource sd on sd.id=sds.datasource
where sd.name='DOAJ-ARTICLES'
) as doaj on doaj.id=r.id
where r.bestlicence in ('Open Access', 'Open Source') and d.type='Institutional Repository' and doaj.id is null)
select distinct result_green.id, true as green
from result_green
union all
select distinct r.id as id, false as green
from ${stats_db_name}.result r
left outer join result_green rg on rg.id=r.id
where rg.id is null;
-- GOLD OA:
-- OA results that have been harvested from a DOAJ journal.
create table ${stats_db_name}.result_gold as
with result_gold as (
select distinct r.id as id
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource
join ${stats_db_name}.datasource_sources sds on sds.id=d.id
join ${stats_db_name}.datasource sd on sd.id=sds.datasource
where r.type='publication' and r.bestlicence='Open Access' and sd.name='DOAJ-Articles')
select distinct result_gold.id, true as gold
from result_gold
union all
select distinct r.id, false as gold
from ${stats_db_name}.result r
where r.id not in (select id from result_gold);

22
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_1-definitions.sql Normal file
View File

@ -0,0 +1,22 @@
----------------------------------------------------
-- Shortcuts for various definitions in stats db ---
----------------------------------------------------
-- Peer reviewed:
create table ${stats_db_name}.result_peerreviewed as
select r.id as id, case when doi.doi_from_crossref=1 and grey.grey_lit=0 then true else false end as peer_reviewed
from ${stats_db_name}.result r
left outer join ${stats_db_name}.indi_pub_doi_from_crossref doi on doi.id=r.id
left outer join ${stats_db_name}.indi_pub_grey_lit grey on grey.id=r.id;
-- Green OA:
create table ${stats_db_name}.result_greenoa as
select r.id, case when green.green_oa=1 then true else false end as green
from ${stats_db_name}.result r
left outer join ${stats_db_name}.indi_pub_green_oa green on green.id=r.id;
-- GOLD OA:
create table ${stats_db_name}.result_gold as
select r.id, case when gold.gold_oa=1 then true else false end as gold
from ${stats_db_name}.result r
left outer join ${stats_db_name}.indi_pub_gold_oa gold on gold.id=r.id;

41
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql
View File

@ -104,25 +104,42 @@ create table TARGET.project_results as select id as result, project as id from T
compute stats TARGET.project_results; compute stats TARGET.project_results;
-- indicators -- indicators
create table TARGET.indi_pub_green_oa as select * from SOURCE.indi_pub_green_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id); create view TARGET.indi_dataset_avg_year_content_oa as select * from SOURCE.indi_dataset_avg_year_content_oa orig;
compute stats TARGET.indi_pub_green_oa; create view TARGET.indi_dataset_avg_year_context_oa as select * from SOURCE.indi_dataset_avg_year_context_oa orig;
create table TARGET.indi_pub_grey_lit as select * from SOURCE.indi_pub_grey_lit orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_grey_lit;
create table TARGET.indi_pub_doi_from_crossref as select * from SOURCE.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_doi_from_crossref;
create table TARGET.indi_pub_gold_oa as select * from SOURCE.indi_pub_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_gold_oa;
create view TARGET.indi_dataset_avg_year_country_oa as select * from SOURCE.indi_dataset_avg_year_country_oa orig; create view TARGET.indi_dataset_avg_year_country_oa as select * from SOURCE.indi_dataset_avg_year_country_oa orig;
create view TARGET.indi_other_avg_year_content_oa as select * from SOURCE.indi_other_avg_year_content_oa orig;
create view TARGET.indi_other_avg_year_context_oa as select * from SOURCE.indi_other_avg_year_context_oa orig;
create view TARGET.indi_other_avg_year_country_oa as select * from SOURCE.indi_other_avg_year_country_oa orig;
create view TARGET.indi_project_datasets_count as select * from SOURCE.indi_project_datasets_count orig; create view TARGET.indi_project_datasets_count as select * from SOURCE.indi_project_datasets_count orig;
create view TARGET.indi_project_otherresearch_count as select * from SOURCE.indi_project_otherresearch_count orig; create view TARGET.indi_project_otherresearch_count as select * from SOURCE.indi_project_otherresearch_count orig;
create view TARGET.indi_project_pubs_count as select * from SOURCE.indi_project_pubs_count orig; create view TARGET.indi_project_pubs_count as select * from SOURCE.indi_project_pubs_count orig;
create view TARGET.indi_project_software_count as select * from SOURCE.indi_project_software_count orig; create view TARGET.indi_project_software_count as select * from SOURCE.indi_project_software_count orig;
create view TARGET.indi_pub_avg_year_content_oa as select * from SOURCE.indi_pub_avg_year_content_oa orig;
create view TARGET.indi_pub_avg_year_context_oa as select * from SOURCE.indi_pub_avg_year_context_oa orig;
create view TARGET.indi_pub_avg_year_country_oa as select * from SOURCE.indi_pub_avg_year_country_oa orig; create view TARGET.indi_pub_avg_year_country_oa as select * from SOURCE.indi_pub_avg_year_country_oa orig;
create table TARGET.indi_pub_green_oa as select * from SOURCE.indi_pub_green_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_green_oa;
create table TARGET.indi_pub_grey_lit as select * from SOURCE.indi_pub_grey_lit orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_grey_lit;
create table TARGET.indi_pub_doi_from_crossref as select * from SOURCE.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_doi_from_crossref;
create table TARGET.indi_pub_gold_oa as select * from SOURCE.indi_pub_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_gold_oa;
create table TARGET.indi_pub_has_abstract as select * from SOURCE.indi_pub_has_abstract orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_has_abstract;
create table TARGET.indi_pub_has_cc_licence as select * from SOURCE.indi_pub_has_cc_licence orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_has_cc_licence;
create table TARGET.indi_pub_has_cc_licence_url as select * from SOURCE.indi_pub_has_cc_licence_url orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.indi_pub_has_cc_licence_url;
create view TARGET.indi_software_avg_year_content_oa as select * from SOURCE.indi_software_avg_year_content_oa orig;
create view TARGET.indi_software_avg_year_context_oa as select * from SOURCE.indi_software_avg_year_context_oa orig;
create view TARGET.indi_software_avg_year_country_oa as select * from SOURCE.indi_software_avg_year_country_oa orig;
--denorm --denorm
alter table TARGET.result rename to TARGET.res_tmp; alter table TARGET.result rename to TARGET.res_tmp;

784
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step21-createObservatoryDB.sql
View File

@ -1,259 +1,561 @@
create table TARGET.result_affiliated_country stored as parquet as create table ${observatory_db_name}.result_cc_licence stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select r.id, coalesce(rln.count, 0) > 0 as cc_licence
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, from ${stats_db_name}.result r
r.peer_reviewed, r.type, c.code as ccode, c.name as cname left outer join (
from SOURCE.result r select rl.id, sum(case when lower(rln.normalized) like 'cc-%' then 1 else 0 end) as count
join SOURCE.result_organization ro on ro.id=r.id from ${stats_db_name}.result_licenses rl
join SOURCE.organization o on o.id=ro.organization left outer join ${stats_db_name}.licenses_normalized rln on rl.type=rln.license
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' group by rl.id
left outer join SOURCE.result_licenses rl on rl.id=r.id ) rln on rln.id=r.id;
left outer join SOURCE.result_pids pids on pids.id=r.id
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, c.code, c.name;
create table TARGET.result_affiliated_year stored as parquet as create table ${observatory_db_name}.result_affiliated_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, r.year count(distinct r.id) as total,
from SOURCE.result r r.green,
join SOURCE.result_organization ro on ro.id=r.id r.gold,
join SOURCE.organization o on o.id=ro.organization case when rl.type is not null then true else false end as licence,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when pids.pid is not null then true else false end as pid,
left outer join SOURCE.result_licenses rl on rl.id=r.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
left outer join SOURCE.result_pids pids on pids.id=r.id r.peer_reviewed,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year; rln.cc_licence,
r.abstract as abstract,
r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, c.code, c.name;
create table TARGET.result_affiliated_year_country stored as parquet as create table ${observatory_db_name}.result_affiliated_year stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, r.year, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_organization ro on ro.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.organization o on o.id=ro.organization case when pids.pid is not null then true else false end as pid,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.peer_reviewed,
left outer join SOURCE.result_pids pids on pids.id=r.id rln.cc_licence,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year, c.code, c.name; r.abstract as abstract,
r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
r.year
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year;
create table TARGET.result_affiliated_datasource stored as parquet as create table ${observatory_db_name}.result_affiliated_year_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, d.name as dname count(distinct r.id) as total,
from SOURCE.result r r.green,
join SOURCE.result_organization ro on ro.id=r.id r.gold,
join SOURCE.organization o on o.id=ro.organization case when rl.type is not null then true else false end as licence,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when pids.pid is not null then true else false end as pid,
left outer join SOURCE.result_datasources rd on rd.id=r.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
left outer join SOURCE.datasource d on d.id=rd.datasource r.peer_reviewed,
left outer join SOURCE.result_licenses rl on rl.id=r.id rln.cc_licence,
left outer join SOURCE.result_pids pids on pids.id=r.id r.abstract as abstract,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name; r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
r.year, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year, c.code, c.name;
create table TARGET.result_affiliated_datasource_country stored as parquet as create table ${observatory_db_name}.result_affiliated_datasource stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, d.name as dname, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_organization ro on ro.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.organization o on o.id=ro.organization case when pids.pid is not null then true else false end as pid,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
left outer join SOURCE.result_datasources rd on rd.id=r.id r.peer_reviewed,
left outer join SOURCE.datasource d on d.id=rd.datasource rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name, c.code, c.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
d.name as dname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_datasources rd on rd.id=r.id
left outer join ${stats_db_name}.datasource d on d.id=rd.datasource
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name;
create table TARGET.result_affiliated_organization stored as parquet as create table ${observatory_db_name}.result_affiliated_datasource_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, o.name as oname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_organization ro on ro.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.organization o on o.id=ro.organization case when pids.pid is not null then true else false end as pid,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.peer_reviewed,
left outer join SOURCE.result_pids pids on pids.id=r.id rln.cc_licence,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name; r.abstract as abstract,
r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
d.name as dname, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_datasources rd on rd.id=r.id
left outer join ${stats_db_name}.datasource d on d.id=rd.datasource
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name, c.code, c.name;
create table TARGET.result_affiliated_organization_country stored as parquet as create table ${observatory_db_name}.result_affiliated_organization stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, o.name as oname, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_organization ro on ro.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.organization o on o.id=ro.organization case when pids.pid is not null then true else false end as pid,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.peer_reviewed,
left outer join SOURCE.result_pids pids on pids.id=r.id rln.cc_licence,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name, c.code, c.name; r.abstract as abstract,
r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
o.name as oname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name;
create table TARGET.result_affiliated_funder stored as parquet as create table ${observatory_db_name}.result_affiliated_organization_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, p.funder as pfunder count(distinct r.id) as total,
from SOURCE.result r r.green,
join SOURCE.result_organization ro on ro.id=r.id r.gold,
join SOURCE.organization o on o.id=ro.organization case when rl.type is not null then true else false end as licence,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when pids.pid is not null then true else false end as pid,
join SOURCE.result_projects rp on rp.id=r.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.project p on p.id=rp.project r.peer_reviewed,
left outer join SOURCE.result_licenses rl on rl.id=r.id rln.cc_licence,
left outer join SOURCE.result_pids pids on pids.id=r.id r.abstract as abstract,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder; r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
o.name as oname, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name, c.code, c.name;
create table TARGET.result_affiliated_funder_country stored as parquet as create table ${observatory_db_name}.result_affiliated_funder stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, p.funder as pfunder, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_organization ro on ro.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.organization o on o.id=ro.organization case when pids.pid is not null then true else false end as pid,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.result_projects rp on rp.id=r.id r.peer_reviewed,
join SOURCE.project p on p.id=rp.project rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder, c.code, c.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
p.funder as pfunder
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
join ${stats_db_name}.result_projects rp on rp.id=r.id
join ${stats_db_name}.project p on p.id=rp.project
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder;
create table TARGET.result_deposited_country stored as parquet as create table ${observatory_db_name}.result_affiliated_funder_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, c.code, c.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
p.funder as pfunder, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_organization ro on ro.id=r.id
join ${stats_db_name}.organization o on o.id=ro.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
join ${stats_db_name}.result_projects rp on rp.id=r.id
join ${stats_db_name}.project p on p.id=rp.project
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder, c.code, c.name;
create table TARGET.result_deposited_year stored as parquet as create table ${observatory_db_name}.result_deposited_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, r.year count(distinct r.id) as total,
from SOURCE.result r r.green,
join SOURCE.result_datasources rd on rd.id=r.id r.gold,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when rl.type is not null then true else false end as licence,
join SOURCE.datasource_organizations dor on dor.id=d.id case when pids.pid is not null then true else false end as pid,
join SOURCE.organization o on o.id=dor.organization case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' r.peer_reviewed,
left outer join SOURCE.result_licenses rl on rl.id=r.id rln.cc_licence,
left outer join SOURCE.result_pids pids on pids.id=r.id r.abstract as abstract,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year; r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, c.code, c.name;
create table TARGET.result_deposited_year_country stored as parquet as create table ${observatory_db_name}.result_deposited_year stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, r.year, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year, c.code, c.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
r.year
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year;
create table TARGET.result_deposited_datasource stored as parquet as create table ${observatory_db_name}.result_deposited_year_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, d.name as dname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
r.year, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year, c.code, c.name;
create table TARGET.result_deposited_datasource_country stored as parquet as create table ${observatory_db_name}.result_deposited_datasource stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, d.name as dname, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name, c.code, c.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
d.name as dname
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name;
create table TARGET.result_deposited_organization stored as parquet as create table ${observatory_db_name}.result_deposited_datasource_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, o.name as oname count(distinct r.id) as total,
from SOURCE.result r r.green,
join SOURCE.result_datasources rd on rd.id=r.id r.gold,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when rl.type is not null then true else false end as licence,
join SOURCE.datasource_organizations dor on dor.id=d.id case when pids.pid is not null then true else false end as pid,
join SOURCE.organization o on o.id=dor.organization case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' r.peer_reviewed,
left outer join SOURCE.result_licenses rl on rl.id=r.id rln.cc_licence,
left outer join SOURCE.result_pids pids on pids.id=r.id r.abstract as abstract,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name; r.authors > 1 as multiple_authors,
rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
d.name as dname, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name, c.code, c.name;
create table TARGET.result_deposited_organization_country stored as parquet as create table ${observatory_db_name}.result_deposited_organization stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, o.name as oname, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
left outer join SOURCE.result_licenses rl on rl.id=r.id r.abstract as abstract,
left outer join SOURCE.result_pids pids on pids.id=r.id r.authors > 1 as multiple_authors,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name, c.code, c.name; rpc.count > 1 as multiple_projects,
rfc.count > 1 as multiple_funders,
r.type,
o.name as oname
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name;
create table TARGET.result_deposited_funder stored as parquet as create table ${observatory_db_name}.result_deposited_organization_country stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, p.funder as pfunder r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
join SOURCE.result_projects rp on rp.id=r.id r.abstract as abstract,
join SOURCE.project p on p.id=rp.project r.authors > 1 as multiple_authors,
left outer join SOURCE.result_licenses rl on rl.id=r.id rpc.count > 1 as multiple_projects,
left outer join SOURCE.result_pids pids on pids.id=r.id rfc.count > 1 as multiple_funders,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder; r.type,
o.name as oname, c.code as ccode, c.name as cname
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name, c.code, c.name;
create table TARGET.result_deposited_funder_country stored as parquet as create table ${observatory_db_name}.result_deposited_funder stored as parquet as
select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, select
case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, count(distinct r.id) as total,
r.peer_reviewed, r.type, p.funder as pfunder, c.code as ccode, c.name as cname r.green,
from SOURCE.result r r.gold,
join SOURCE.result_datasources rd on rd.id=r.id case when rl.type is not null then true else false end as licence,
join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') case when pids.pid is not null then true else false end as pid,
join SOURCE.datasource_organizations dor on dor.id=d.id case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
join SOURCE.organization o on o.id=dor.organization r.peer_reviewed,
join SOURCE.country c on c.code=o.country and c.continent_name='Europe' rln.cc_licence,
join SOURCE.result_projects rp on rp.id=r.id r.abstract as abstract,
join SOURCE.project p on p.id=rp.project r.authors > 1 as multiple_authors,
left outer join SOURCE.result_licenses rl on rl.id=r.id rpc.count > 1 as multiple_projects,
left outer join SOURCE.result_pids pids on pids.id=r.id rfc.count > 1 as multiple_funders,
group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder, c.code, c.name; r.type,
p.funder as pfunder
from ${stats_db_name}.result r
join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
join ${stats_db_name}.result_projects rp on rp.id=r.id
join ${stats_db_name}.project p on p.id=rp.project
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder;
compute stats TARGET.result_affiliated_country; create table ${observatory_db_name}.result_deposited_funder_country stored as parquet as
compute stats TARGET.result_affiliated_year; select
compute stats TARGET.result_affiliated_year_country; count(distinct r.id) as total,
compute stats TARGET.result_affiliated_datasource; r.green,
compute stats TARGET.result_affiliated_datasource_country; r.gold,
compute stats TARGET.result_affiliated_organization; case when rl.type is not null then true else false end as licence,
compute stats TARGET.result_affiliated_organization_country; case when pids.pid is not null then true else false end as pid,
compute stats TARGET.result_affiliated_funder; case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa,
compute stats TARGET.result_affiliated_funder_country; r.peer_reviewed,
compute stats TARGET.result_deposited_country; rln.cc_licence,
compute stats TARGET.result_deposited_year; r.abstract as abstract,
compute stats TARGET.result_deposited_year_country; r.authors > 1 as multiple_authors,
compute stats TARGET.result_deposited_datasource; rpc.count > 1 as multiple_projects,
compute stats TARGET.result_deposited_datasource_country; rfc.count > 1 as multiple_funders,
compute stats TARGET.result_deposited_organization; r.type,
compute stats TARGET.result_deposited_organization_country; p.funder as pfunder, c.code as ccode, c.name as cname
compute stats TARGET.result_deposited_funder; from ${stats_db_name}.result r
compute stats TARGET.result_deposited_funder_country; join ${stats_db_name}.result_datasources rd on rd.id=r.id
join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository')
join ${stats_db_name}.datasource_organizations dor on dor.id=d.id
join ${stats_db_name}.organization o on o.id=dor.organization
join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe'
join ${stats_db_name}.result_projects rp on rp.id=r.id
join ${stats_db_name}.project p on p.id=rp.project
left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id
left outer join ${stats_db_name}.result_pids pids on pids.id=r.id
left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id
left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id
left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id
group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end,
case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract,
cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder, c.code, c.name;

114
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
View File

@ -239,14 +239,51 @@
<param>stats_db_name=${stats_db_name}</param> <param>stats_db_name=${stats_db_name}</param>
<param>openaire_db_name=${openaire_db_name}</param> <param>openaire_db_name=${openaire_db_name}</param>
</hive2> </hive2>
<ok to="Step16"/> <ok to="Step15_5"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="Step16"> <action name="Step15_5">
<hive2 xmlns="uri:oozie:hive2-action:0.1"> <hive2 xmlns="uri:oozie:hive2-action:0.1">
<jdbc-url>${hive_jdbc_url}</jdbc-url> <jdbc-url>${hive_jdbc_url}</jdbc-url>
<script>scripts/step16.sql</script> <script>scripts/step15_5.sql</script>
<param>stats_db_name=${stats_db_name}</param>
<param>openaire_db_name=${openaire_db_name}</param>
</hive2>
<ok to="Contexts"/>
<error to="Kill"/>
</action>
<action name="Contexts">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>contexts.sh</exec>
<argument>${context_api_url}</argument>
<argument>${stats_db_name}</argument>
<file>contexts.sh</file>
</shell>
<ok to="Step16-createIndicatorsTables"/>
<error to="Kill"/>
</action>
<action name="Step16-createIndicatorsTables">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>indicators.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${wf:appPath()}/scripts/step16-createIndicatorsTables.sql</argument>
<file>indicators.sh</file>
</shell>
<ok to="Step16_1-definitions"/>
<error to="Kill"/>
</action>
<action name="Step16_1-definitions">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<jdbc-url>${hive_jdbc_url}</jdbc-url>
<script>scripts/step16_1-definitions.sql</script>
<param>stats_db_name=${stats_db_name}</param> <param>stats_db_name=${stats_db_name}</param>
<param>openaire_db_name=${openaire_db_name}</param> <param>openaire_db_name=${openaire_db_name}</param>
</hive2> </hive2>
@ -261,48 +298,11 @@
<param>stats_db_name=${stats_db_name}</param> <param>stats_db_name=${stats_db_name}</param>
<param>openaire_db_name=${openaire_db_name}</param> <param>openaire_db_name=${openaire_db_name}</param>
</hive2> </hive2>
<ok to="Step16_6"/> <ok to="Step19-finalize"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="Step16_6"> <action name="Step19-finalize">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<jdbc-url>${hive_jdbc_url}</jdbc-url>
<script>scripts/step16_6.sql</script>
<param>stats_db_name=${stats_db_name}</param>
<param>openaire_db_name=${openaire_db_name}</param>
</hive2>
<ok to="Step16_7-createIndicatorsTables"/>
<error to="Kill"/>
</action>
<action name="Step16_7-createIndicatorsTables">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>indicators.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${wf:appPath()}/scripts/step16_7-createIndicatorsTables.sql</argument>
<file>indicators.sh</file>
</shell>
<ok to="Step17"/>
<error to="Kill"/>
</action>
<action name="Step17">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>contexts.sh</exec>
<argument>${context_api_url}</argument>
<argument>${stats_db_name}</argument>
<file>contexts.sh</file>
</shell>
<ok to="Step19"/>
<error to="Kill"/>
</action>
<action name="Step19">
<shell xmlns="uri:oozie:shell-action:0.1"> <shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker> <job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node> <name-node>${nameNode}</name-node>
@ -326,20 +326,44 @@
<argument>${wf:appPath()}/scripts/step20-createMonitorDB.sql</argument> <argument>${wf:appPath()}/scripts/step20-createMonitorDB.sql</argument>
<file>monitor.sh</file> <file>monitor.sh</file>
</shell> </shell>
<ok to="step21-createObservatoryDB-pre"/>
<error to="Kill"/>
</action>
<action name="step21-createObservatoryDB-pre">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>observatory-pre.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${observatory_db_name}</argument>
<argument>${observatory_db_shadow_name}</argument>
<file>observatory-pre.sh</file>
</shell>
<ok to="step21-createObservatoryDB"/> <ok to="step21-createObservatoryDB"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="step21-createObservatoryDB"> <action name="step21-createObservatoryDB">
<hive2 xmlns="uri:oozie:hive2-action:0.1">
<jdbc-url>${hive_jdbc_url}</jdbc-url>
<script>scripts/step21-createObservatoryDB.sql</script>
<param>stats_db_name=${stats_db_name}</param>
<param>observatory_db_name=${observatory_db_name}</param>
</hive2>
<ok to="step21-createObservatoryDB-post"/>
<error to="Kill"/>
</action>
<action name="step21-createObservatoryDB-post">
<shell xmlns="uri:oozie:shell-action:0.1"> <shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker> <job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node> <name-node>${nameNode}</name-node>
<exec>observatory.sh</exec> <exec>observatory-post.sh</exec>
<argument>${stats_db_name}</argument> <argument>${stats_db_name}</argument>
<argument>${observatory_db_name}</argument> <argument>${observatory_db_name}</argument>
<argument>${observatory_db_shadow_name}</argument> <argument>${observatory_db_shadow_name}</argument>
<argument>${wf:appPath()}/scripts/step21-createObservatoryDB.sql</argument> <file>observatory-post.sh</file>
<file>observatory.sh</file>
</shell> </shell>
<ok to="Step22"/> <ok to="Step22"/>
<error to="Kill"/> <error to="Kill"/>